Skip to main content
Glama

Several actions in one call

browser_actions
Destructive

Runs several browser steps in one call, such as filling form fields and submitting, stopping at the first failure or page change and returning per-step results with screen evidence.

Instructions

Several steps in order in one call, e.g. fill a form's fields and submit it; each gets the same checks as its own tool. Stops at the first that fails, or after one that moves the page to another address (later refs would belong to the old page). Returns a line per step and the evidence and visible screen after the last one run.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "actions": "<actions>"
    },
    "name": "browser_actions"
  }
}

Input Schema

NameRequiredDescriptionDefault
actionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already flag this as a destructive, open-world write, and the description adds real behavior beyond that: sequential execution, fail-fast semantics, the navigation cutoff that invalidates later refs, and the return shape (a line per step plus evidence and the visible screen). It does not discuss how partial success is reported or whether completed steps can be undone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two dense sentences with no filler: purpose first, then stopping rules, then return value. The parenthetical about stale refs earns its place by warning of a concrete hazard.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a nested batch-execution tool with no output schema and thin annotations, the description covers the essentials — sequencing, abort conditions, and what comes back. The gaps (per-item field meanings, item limit, partial-failure detail) are real but secondary.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema's top-level 'actions' property has no description and coverage is low, so the description has to compensate. It adds useful semantics (steps run in order, stop on failure or navigation, refs belong to the pre-navigation page) but never explains the per-item fields, the ref format, or the 10-step ceiling, so the item-level contract stays under-specified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific capability: executing several browser steps in order within one call, with a concrete example (fill a form's fields and submit). It implicitly distinguishes itself from the single-action siblings by saying each step 'gets the same checks as its own tool', though it never names an alternative tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear context for when to use it — when you have several sequential steps — and it explains the stopping conditions (first failure, or a step that navigates) that tell an agent when batching is unsafe. It does not explicitly say to fall back to single-action tools for one step, but that is strongly implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.